Hi,

On 04.07.2018 10:34, Christoph Hormann wrote:
> As i have been very clear about this is not the case:
> 
>>> Microsoft's process documentation contains a number of hints that
>>> indicate things can go wrong in the process in ways that are likely
>>> to produce significant errors of kinds that are very unlikely to
>>> happen in manual mapping.

What you are suspecting here seems to have manifested itself in Alaska,
where one reviewer claims that most (!) buildings in the dataset do not
correspond to anything on the imagery available to us, and the few (!)
objects that do differ wildly in shape:

https://github.com/Microsoft/USBuildingFootprints/issues/23

Bye
Frederik

-- 
Frederik Ramm  ##  eMail [email protected]  ##  N49°00'09" E008°23'33"

_______________________________________________
Imports mailing list
[email protected]
https://lists.openstreetmap.org/listinfo/imports

Reply via email to